A method performed by an electronic device is described. The method includes generating a depth map of a scene external to a vehicle. The method also includes performing first processing in a first direction of a depth map to determine a first non-obstacle estimation of the scene. The method also includes performing second processing in a second direction of the depth map to determine a second non-obstacle estimation of the scene. The method further includes combining the first non-obstacle estimation and the second non-obstacle estimation to determine a non-obstacle map of the scene. The combining includes combining comprises selectively using a first reliability map of the first processing and/or a second reliability map of the second processing The method additionally includes navigating the vehicle using the non-obstacle map.

A method for identifying a cause of blockage in a sequence of images provided by a camera of a vehicle, the method comprising iteratively: S10) acquiring an image of the camera; successively acquired images forming a sequence of images; S20) detecting a blockage in last images of the sequence of images; S60) determining whether it is day-time or night-time based on time information; if it is determined that it is night-time: S82) determining whether toggling front light(s) of the vehicle on/off causes a change in images acquired by the camera; and S84) in this case, determining that for the current iteration, the cause of the blockage is presumably the road being dark. A computer program for performing said method, a computer-readable recording medium containing such computer program, a driving assistance system capable of executing said method.

A method of processing data for a driving automation system, the method comprising steps of: obtaining sound data from a microphone of an autonomous vehicle; processing the sound data to obtain a sound characteristic; and updating a context of the autonomous vehicle based on the sound characteristic.

A method for generating training data is disclosed. The method may include executing a simulation process. The simulation process may include traversing a virtual, forward-looking sensor over a virtual road surface defining at least one virtual railroad crossing. During the traversing, the virtual sensor may be moved with respect to the virtual road surface as dictated by a vehicle-motion model modeling motion of a vehicle driving on the virtual road surface while carrying the virtual sensor. Virtual sensor data characterizing the virtual road surface may be recorded. The virtual sensor data may correspond to what a real sensor would have output had it sensed the road surface in the real world.

An approach is provided for using a machine learning model for identifying planar region(s) in an image. The approach involves, for example, determining the model for performing image segmentation. The model comprises at least: a trainable filter that convolves the image to generate an input volume comprising a projection of the image at different resolution scales; and feature(s) to identify image region(s) having a texture within a similarity threshold. The approach also involves processing the image using the model by generating the input volume from the image using the trainable filter and extracting the feature(s) from the input volume to determine the region(s) having the texture. The approach further involves determining the planar region(s) by clustering the image regions. The approach further involves generating a planar mask based on the planar region(s). The approach further involves providing the planar mask as an output of the image segmentation.

In a road parameter estimation apparatus, a marker-based estimator extracts, based on markers extracted by a marker extractor, at least one lane line that demarcates a road into plural regions in a width direction of the road, and estimates, based on the extracted at least one lane line, a value of at least one feature parameter of the road as a maker-based estimation result. The at least one feature parameter of the road represents at least one feature of the road. A model-based estimator estimates, based on the at least one model-based demarcation line, a value of the at least one feature parameter of the road parameter as a model-based estimation result. A determiner compares the at least one lane line with the model-based demarcation line to accordingly determine whether to use the marker-based estimation result or the model-based estimation result.

A division line recognition apparatus is provided with a feature detector detecting bright features showing an area which is brighter than a road surface from captured images, and a reflection determination unit which determines straight lines as road surface reflection areas, when the bright feature points are detected in a same position between frames of images captured at a preset period and form a straight line shorter than a preset threshold length, among the detected bright feature points. A white line recognition unit which recognizes a white line from the bright feature points having the bright feature points showing a short line determined as the road surface reflection, removed therefrom.

Techniques for a perception system of a vehicle that can detect and track objects in an environment are described herein. The perception system may include a machine-learned model that includes one or more different portions, such as different components, subprocesses, or the like. In some instances, the techniques may include training the machine-learned model end-to-end such that outputs of a first portion of the machine-learned model are tailored for use as inputs to another portion of the machine-learned model. Additionally, or alternatively, the perception system described herein may utilize temporal data to track objects in the environment of the vehicle and associate tracking data with specific objects in the environment detected by the machine-learned model. That is, the architecture of the machine-learned model may include both a detection portion and a tracking portion in the same loop.

Systems and methods are provided for navigating a host vehicle. In an embodiment, a processing device may be configured to receive images captured over a time period; analyze images to identify a target vehicle; receive map information associated including a plurality of target trajectories; determine, based on analysis of the images, first and second estimated positions of the target vehicle within the time period; determine, based on the first and second estimated positions, a trajectory of the target vehicle over the time period; compare the determined trajectory to the plurality of target trajectories to identify a target trajectory traversed by the target vehicle; determine, based on the identified target trajectory, a position of the target vehicle; and determine a navigational action for the host vehicle based on the determined position.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for agent trajectory prediction using anchor trajectories.